Conference proceeding
Transfer Learning for Segmentation of Injured Lungs Using Coarse-to-Fine Convolutional Neural Networks
Image Analysis for Moving Organ, Breast, and Thoracic Images, Vol.11040, pp.191-201
Lecture Notes in Computer Science
International Workshop on Reconstruction and Analysis of Moving Body Organs
2018
DOI: 10.1007/978-3-030-00946-5_20
Abstract
Deep learning using convolutional neural networks (ConvNets) achieves high accuracy across many computer vision tasks, with the ability to learn multi-scale features and generalize across a variety of input data. In this work, we propose a deep learning framework that utilizes a coarse-to-fine cascade of 3D ConvNet models for segmentation of lung structures obtained from computed tomographic (CT) images. Deep learning requires a large number of training datasets, which may be challenging in medical imaging, especially for rare diseases. In the present study, transfer learning is utilized for lung segmentation of CT scans in large animal models of the acute respiratory distress syndrome (ARDS) using only 13 subjects. The method was quantitatively evaluated on a human dataset, consisting of 395 3D CT scans from 153 subjects, and an animal dataset consisting of 148 3D CT images from 5 porcine subjects. The human dataset achieved an average Jacaard index of 0.99, and an average symmetric surface distance (ASSD) of 0.29 mm. The animal dataset had an average Jacaard index of 0.94, and an ASSD of 0.99 mm.
Details
- Title: Subtitle
- Transfer Learning for Segmentation of Injured Lungs Using Coarse-to-Fine Convolutional Neural Networks
- Creators
- Sarah E Gerard - University of Iowa, Roy J. Carver Department of Biomedical EngineeringJacob Herrmann - University of Iowa, Roy J. Carver Department of Biomedical EngineeringDavid W Kaczka - University of Iowa, AnesthesiaJoseph M Reinhardt - University of Iowa, Roy J. Carver Department of Biomedical Engineering
- Contributors
- Danail Stoyanov (Editor)Zeike Taylor (Editor)Bernhard Kainz (Editor)Gabriel Maicas (Editor)Reinhard R Beichel (Editor)Anne Martel (Editor)Lena Maier-Hein (Editor)Kanwal Bhatia (Editor)Tom Vercauteren (Editor)Ozan Oktay (Editor)Gustavo Carneiro (Editor)Andrew P Bradley (Editor)Jacinto Nascimento (Editor)Hang Min (Editor)Matthew S Brown (Editor)Colin Jacobs (Editor)Bianca Lassen-Schmidt (Editor)Kensaku Mori (Editor)Jens Petersen (Editor)Raúl San José Estépar (Editor)Alexander Schmidt-Richberg (Editor)Catarina Veiga (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- Image Analysis for Moving Organ, Breast, and Thoracic Images, Vol.11040, pp.191-201
- Conference
- International Workshop on Reconstruction and Analysis of Moving Body Organs
- Publisher
- Springer International Publishing; Cham
- Series
- Lecture Notes in Computer Science
- DOI
- 10.1007/978-3-030-00946-5_20
- Language
- English
- Date published
- 2018
- Academic Unit
- Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Radiology; Anesthesia
- Record Identifier
- 9984006440502771
Metrics
25 Record Views